Using genetic algorithms to select architecture of a feedforward artificial neural network

Date

2001

Authors

Arifovic, J.
Gençay, R.

Editor(s)

Advisor

Supervisor

Co-Advisor

Co-Supervisor

Instructor

Source Title

Physica A : Statistical Mechanics and its Applications

Print ISSN

0378-4371

Electronic ISSN

1873-2119

Publisher

Elsevier BV

Volume

289

Issue

3-4

Pages

574 - 594

Language

English

Journal Title

Journal ISSN

Volume Title

Series

Abstract

This paper proposes a model selection methodology for feedforward network models based on the genetic algorithms and makes a number of distinct but inter-related contributions to the model selection literature for the feedforward networks. First, we construct a genetic algorithm which can search for the global optimum of an arbitrary function as the output of a feedforward network model. Second, we allow the genetic algorithm to evolve the type of inputs, the number of hidden units and the connection structure between the inputs and the output layers. Third, we study how introduction of a local elitist procedure which we call the election operator affects the algorithm's performance. We conduct a Monte Carlo simulation to study the sensitiveness of the global approximation properties of the studied genetic algorithm. Finally, we apply the proposed methodology to the daily foreign exchange returns.

Course

Other identifiers

Book Title

Citation